Palavras-chave
Machine learning
Abdômen agudo
Diagnóstico diferencial
Tomografia computadorizada
Como Citar
Copyright © | Todos os direitos reservados.
A revista detém os direitos autorais exclusivos de publicação deste artigo nos termos da lei 9610/98.
Reprodução parcial
É livre o uso de partes do texto, figuras e questionário do artigo, sendo obrigatória a citação dos autores e revista.
Reprodução total
É expressamente proibida, devendo ser autorizada pela revista.
Resumo
Objetivo: Sintetizar sobre o uso da inteligência artificial e do machine learning no diagnóstico diferencial, na estratificação de risco e no suporte à decisão clínica e cirúrgica em pacientes com abdômen agudo. Métodos: Trata-se de uma revisão integrativa conduzida conforme as diretrizes PRISMA. A busca foi realizada na base de dados PubMed utilizando descritores relacionados à inteligência artificial, machine learning, diagnóstico e abdômen agudo. Foram incluídos estudos publicados entre 2023 e 2026 que avaliaram a aplicação dessas tecnologias em pacientes com abdômen agudo. Resultados: Foram selecionados 11 estudos, os quais demonstraram resultados promissores na identificação de doenças abdominais agudas, estratificação de risco, predição de sepse, mortalidade e complicações cirúrgicas, além do suporte à interpretação de exames de imagem. Os modelos apresentaram bom desempenho em diferentes contextos clínicos e cirúrgicos. Considerações finais: A inteligência artificial e o machine learning apresentam potencial para auxiliar o diagnóstico diferencial e a tomada de decisão no manejo do abdômen agudo, atuando como ferramentas complementares à avaliação clínica. Entretanto, são necessários estudos adicionais para validação clínica e externa desses modelos.
Referências
BETTE S, et al. Radiomics-Based Machine Learning Model for Diagnosis of Acute Pancreatitis Using Computed Tomography. Diagnostics (Basel), 2024; 14(7): 718.
BMJ Best Practice. Abdominal pain. BMJ Best Practice, 2026.
BRODER J, et al. Guidelines for Reasonable and Appropriate Care in the Emergency Department 2 (GRACE-2): Low-risk, recurrent abdominal pain in the emergency department. Academic Emergency Medicine, 2022; 29(7): 869-882.
CHEN B, et al. Machine learning based peri-surgical risk calculator for abdominal related emergency general surgery: a multicenter retrospective study. International Journal of Surgery, 2024; 110(6): 3527-3535.
CHOI HU, et al. Diagnostic performance and image quality of an image-based denoising algorithm applied to radiation dose-reduced CT in diagnosing acute appendicitis. Abdominal Radiology, 2024; 49(6): 1839-1849.
DU L, et al. Development and validation of a machine learning-based nomogram model integrating LASSO regression and multiple evaluation methods for predicting early sepsis risk in acute abdomen. European Journal of Medical Research, 2026; 31: 464.
GAN T, et al. Machine learning based prediction models for analyzing risk factors in patients with acute abdominal pain: a retrospective study. Frontiers in Medicine, 2024; 11: 1354925.
HAMEDI Z, et al. AI-Based Analysis of Abdominal Ultrasound Images to Support Medical Diagnosis in Emergency Departments. Studies in Health Technology and Informatics, 2025; 325: 16-21.
HEEN AF, et al. Machine Learning for Decision-Support in Acute Abdominal Pain: Proof of Concept and Central Considerations. Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren, 2023.
ISSAIY, M., et al., Artificial Intelligence and Acute Appendicitis: A Systematic Review of Diagnostic and Prognostic Models. World Journal of Emergency Surgery, 2023; 18(1): 59.
KIRUBARAJAN A, et al. Artificial intelligence in emergency medicine: A scoping review. Journal of the American College of Emergency Physicians Open, 2020; 1(6): 1691-1702.
LIU Z, et al. Intelligent prediagnosis for nontraumatic acute abdomen with surface-level information using machine learning. Science Progress, 2025; 108(2): 368504251350763.
NEWMAN-TOKER DE, et al. Diagnostic Errors in the Emergency Department: A Systematic Review. Diagnosis, 2022.
PIEBPIEN P, et al. Can machine learning models improve the prediction of surgical site infection in abdominal surgery than traditional statistical models? Journal of International Medical Research, 2024; 52(11): 3000605241293696.
RAGAB H, et al. Artificial Intelligence in Abdominal MRI Diagnostics: Current Applications, Challenges, and Future Perspectives. Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren, 2026.
ROWE SP, et al. The future of radiology: What if artificial intelligence is really as good as predicted? Diagnostic and Interventional Imaging, Volume 103, Issue 9, 2022.
SARTELLI M, et al. The management of intra-abdominal infections from a global perspective: 2017 WSES guidelines for management of intra-abdominal infections. World Journal of Emergency Surgery, 2017; 12: 29.
SINGER M, et al. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA, 2016; 315(8): 801-810.
TAKAISHI T, et al. Deep learning for appendicitis: development of a three-dimensional localization model on CT. Japanese Journal of Radiology, 2025; 43(11): 1859-1869.
TOPOL EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 2019; 25(1): 44-56.
XIANG K, SHANG D. Construction of a Multi-View Deep Learning Model for the Severity Classification of Acute Pancreatitis. Discovery Medicine, 2025; 37(192): 73-92.
WEI W, et al. Construction of a clinical prediction model for complicated appendicitis based on machine learning techniques. Scientific Reports, 2024; 14(1): 16473.
WORLD HEALTH ORGANIZATION. Ethics and Governance of Artificial Intelligence for Health: WHO Guidance. Geneva: World Health Organization, 2021.
WOLFE JM, et al. Abdominal Pain in the Emergency Department: How to Select the Correct Imaging for Diagnosis. Open Access Emergency Medicine, 2022; 14: 789-800.